Image de couverture de livre

Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Tian, Yuandong
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
par: Lyu, Kaifeng, et autres
Publié: (2023)

The Path Not Taken: RLVR Provably Learns Off the Principals
par: Zhu, Hanqing, et autres
Publié: (2025)

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking
par: Xu, Yongzhong
Publié: (2026)

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
par: Gaitonde, Jason, et autres
Publié: (2026)

The Norm-Separation Delay Law of Grokking: A First-Principles Theory of Delayed Generalization
par: Khanh, Truong Xuan, et autres
Publié: (2026)

Grokking vs. Learning: Same Features, Different Encodings
par: Manning-Coe, Dmitry, et autres
Publié: (2025)

Topological Signatures of Grokking
par: Tang, Yifan, et autres
Publié: (2026)

Feature Repulsion and Spectral Lock-in: An Empirical Study of Two-Layer Network Grokking
par: Xu, Yongzhong
Publié: (2026)

First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation
par: Khanh, Truong Xuan, et autres
Publié: (2026)

On Implications of Scaling Laws on Feature Superposition
par: Katta, Pavan
Publié: (2024)

Provable Benefit of Cutout and CutMix for Feature Learning
par: Oh, Junsoo, et autres
Publié: (2024)

Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking
par: Rashidinejad, Paria, et autres
Publié: (2024)

Provable Scaling Laws for the Test-Time Compute of Large Language Models
par: Chen, Yanxi, et autres
Publié: (2024)

Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning
par: Ding, Zihan, et autres
Publié: (2024)

Grokking Explained: A Statistical Phenomenon
par: Carvalho, Breno W., et autres
Publié: (2025)

Grokking in Linear Models for Logistic Regression
par: Das, Nataraj, et autres
Publié: (2026)

Controlling Grokking with Nonlinearity and Data Symmetry
par: Salah, Ahmed, et autres
Publié: (2024)

Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
par: Ding, Meng, et autres
Publié: (2026)

A Principled Loss Function for Direct Language Model Alignment
par: Tan, Yuandong
Publié: (2025)

GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection
par: Su, DiJia, et autres
Publié: (2025)

Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation
par: Park, Yeachan, et autres
Publié: (2024)

Multi-objective Optimization by Learning Space Partitions
par: Zhao, Yiyang, et autres
Publié: (2021)

Grokfast: Accelerated Grokking by Amplifying Slow Gradients
par: Lee, Jaerin, et autres
Publié: (2024)

Understanding Grokking Through A Robustness Viewpoint
par: Tan, Zhiquan, et autres
Publié: (2023)

Progress Measures for Grokking on Real-world Tasks
par: Golechha, Satvik
Publié: (2024)

Grokking and Generalization Collapse: Insights from \texttt{HTSR} theory
par: Prakash, Hari K., et autres
Publié: (2025)

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
par: Chou, Chi-Ning, et autres
Publié: (2026)

Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
par: Banerjee, Arko, et autres
Publié: (2024)

Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
par: Tian, Yuandong
Publié: (2024)

Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation
par: Salah, Ahmed, et autres
Publié: (2025)

The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold
par: Musat, Tiberiu
Publié: (2025)

NeuralGrok: Accelerate Grokking by Neural Gradient Transformation
par: Zhou, Xinyu, et autres
Publié: (2025)

Towards General-Purpose Model-Free Reinforcement Learning
par: Fujimoto, Scott, et autres
Publié: (2025)

Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
par: Chen, Siyu, et autres
Publié: (2024)

Muon Optimizer Accelerates Grokking
par: Tveit, Amund, et autres
Publié: (2025)

Grokking Finite-Dimensional Algebra
par: Notsawo, Pascal Jr Tikeng, et autres
Publié: (2026)

Grokking Group Multiplication with Cosets
par: Stander, Dashiell, et autres
Publié: (2023)

Unifying Learning Dynamics and Generalization in Transformers Scaling Law
par: Yang, Chiwun
Publié: (2025)

Early-Warning Signals of Grokking via Loss-Landscape Geometry
par: Xu, Yongzhong
Publié: (2026)

Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
par: Hidajat, Kai, et autres
Publié: (2026)